SOTAVerified

Visual Tracking

Visual Tracking is an essential and actively researched problem in the field of computer vision with various real-world applications such as robotic services, smart surveillance systems, autonomous driving, and human-computer interaction. It refers to the automatic estimation of the trajectory of an arbitrary target object, usually specified by a bounding box in the first frame, as it moves around in subsequent video frames.

Source: Learning Reinforced Attentional Representation for End-to-End Visual Tracking

Papers

Showing 226250 of 525 papers

TitleStatusHype
Efficient Adversarial Attacks for Visual Object Tracking0
Unsupervised Deep Representation Learning for Real-Time TrackingCode1
Scale Equivariance Improves Siamese TrackingCode1
Visual Tracking by TridentAlign and Context EmbeddingCode1
Tracking-by-Trackers with a Distilled and Reinforced ModelCode1
Alpha-Refine: Boosting Tracking Performance by Precise Bounding Box EstimationCode1
Accurate Bounding-box Regression with Distance-IoU Loss for Visual Tracking0
The Heterogeneity Hypothesis: Finding Layer-Wise Differentiated Network ArchitecturesCode1
Exemplar Loss for Siamese Network in Visual Tracking0
Cascaded Regression Tracking: Towards Online Hard Distractor Discrimination0
Deep Convolutional Likelihood Particle Filter for Visual Tracking0
Variational Inference and Learning of Piecewise-linear Dynamical Systems0
TLPG-Tracker: Joint Learning of Target Localization and Proposal Generation for Visual Tracking.0
One-Shot Adversarial Attacks on Visual Tracking With Dual Attention0
Correlation-Guided Attention for Corner Detection Based Visual Tracking0
Robust Visual Object Tracking with Two-Stream Residual Convolutional Networks0
How to Train Your Energy-Based Model for RegressionCode1
Derivation of a Constant Velocity Motion Model for Visual Tracking0
Fully Convolutional Online TrackingCode1
Distilling Localization for Self-Supervised Representation Learning0
Beyond Background-Aware Correlation Filters: Adaptive Context Modeling by Hand-Crafted and Deep RGB Features for Visual Tracking0
Efficient Scale Estimation Methods using Lightweight Deep Convolutional Neural Networks for Visual Tracking0
Effective Fusion of Deep Multitasking Representations for Robust Visual Tracking0
High-Performance Long-Term Tracking with Meta-UpdaterCode1
Progressive Multi-Stage Learning for Discriminative Tracking0
Show:102550
← PrevPage 10 of 21Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1ARTrack-LAUC60.3Unverified
2UNINEXT-HAUC59.3Unverified
3JointNLTAUC56.9Unverified
4OSTrackAUC55.9Unverified
5TransTAUC50.7Unverified
6AdaSwitcherAUC42Unverified
#ModelMetricClaimedVerifiedStatus
1TAPIR (Panning MOVi-E)Average Jaccard61.3Unverified
2TAPIR (MOVi-E)Average Jaccard59.8Unverified
#ModelMetricClaimedVerifiedStatus
1TAPIR (Panning MOVi-E)Average Jaccard57.2Unverified
2TAPIR (MOVi-E)Average Jaccard57.1Unverified
#ModelMetricClaimedVerifiedStatus
1TAPIR (Panning MOVi-E)Average Jaccard84.7Unverified
2TAPIR (MOVi-E)Average Jaccard84.3Unverified
#ModelMetricClaimedVerifiedStatus
1TAPIR (MOVi-E)Average Jaccard66.2Unverified
2TAPIR (Panning MOVi-E)Average Jaccard62.7Unverified
#ModelMetricClaimedVerifiedStatus
1TATrack-LAUC71.1Unverified
#ModelMetricClaimedVerifiedStatus
1SiamFC-lu (Ours)AUC0.32Unverified
#ModelMetricClaimedVerifiedStatus
1SiamFC-lu (Ours)AUC0.66Unverified
#ModelMetricClaimedVerifiedStatus
1MDNetScore0.64Unverified
#ModelMetricClaimedVerifiedStatus
1TATrack-LACCURACY0.85Unverified